Search Results

The Mercy babyTAPE device is intended for use by health care professionals to estimate the body weight of infants between the ages of 0 days (birth) and 90 days, using circumferential measurements from specific anatomical landmarks made with the Mercy babyTAPE device for head and chest circumference.

Head: place the Mercy babyTAPE across the frontal bones, slightly above eyebrows and ears, over the occipital prominence, perpendicular to the long axis of the face.

Chest: place the Mercy babyTAPE around the upper torso, passing under the axilla and by the xyphoid process at the level of the nipple. Measure at end-exhalation.

The Mercy babyTAPE device consists of a semi-durable or disposable flexible strip of paper, coated paper, fabric or plastic tape printed on both sides such that one side uses yellow color to indicate its use for the head circumference measurement, while the other side is printed with blue color to indicate its use for the chest circumference measurement. The start end of the device is indicated with color contrasting arrowheads that span the width of the device. Numbered bins are marked on each side proportional to the fractional body weight of newborn and infant patients. The markings correspond to a validated Mercy babyTAPE Method (calculation algorithm) for determining estimated infant body weight.

The Mercy babyTAPE device is intended for health care professionals to estimate the body weight of infants (0-90 days old) using head and chest circumference measurements. The device is a flexible strip of tape with numbered bins, printed on both sides (yellow for head, blue for chest), and the measurements are used with a validated algorithm to estimate weight.

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

The document mentions a "predictive performance study" that evaluated the babyTAPE device's predicted weights against measured weights. It also refers to "Study TAP02" which was used to derive the algorithm. The validation data subset from Study TAP02 appears to be the most relevant "test set" for the final performance evaluation.

• Test Set Sample Size: 416 infants (listed as the validation group in TAP02).
• Data Provenance: The algorithm was developed using data from "2097 US infants at 8 sites" (Study NICHD-2014-TAP02). The predictive performance study described seems to be a validation of this algorithm. The study was likely prospective as it involved obtaining anthropometric data for the purpose of algorithm development and validation. The country of origin is the USA.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

The ground truth for the test set was established using "weight measured on a calibrated scale." This implies direct measurement rather than expert interpretation. Therefore, experts were not involved in establishing the ground truth measurements themselves, but rather in conducting these measurements accurately. The document does not specify the qualifications of the individuals performing the weight measurements.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

Not applicable. The ground truth was direct weight measurement on a calibrated scale, which typically does not involve adjudication.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described. This device is a manual measurement tool with an integrated algorithm, not an AI system designed to assist human readers in image interpretation or diagnosis. The study focused on the accuracy of the device's predicted weight compared to actual weight.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The performance study evaluated the "baby TAPE device predicted weights with weight measured on a calibrated scale." The device itself incorporates the measurement (human-in-the-loop for taking circumference measurements) and then uses the algorithm to provide the predicted weight. Therefore, it's not purely "algorithm-only" in the sense of a fully automated system without any human interaction. However, the reported performance metrics (regression slope, mean error, percentage accuracy) directly assess the output of the device's algorithm given the anthropometric inputs. The comparison to the "reference measuring tape estimated weight" suggests a direct comparison of the Mercy babyTAPE algorithm's performance against another established method.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The ground truth used was actual measured body weights obtained using a calibrated scale.

8. The sample size for the training set

The algorithm was developed using demographic and anthropometric data from Study TAP02.

• Training Set Sample Size: 1681 infants (for model development).

9. How the ground truth for the training set was established

For the training set (Study NICHD-2014-TAP02), the ground truth for weight was established via direct measurement of infant weight and various circumferential and segmental anthropometric measures. These measurements were used to derive the algorithm. This would involve using calibrated measuring tools by trained personnel. The study explicitly states, "Data [was] derived from 2097 US infants (n = 1681 for model development, n = 416 for validation)." It further details the types of measurements taken.

Ask a specific question about this device

The Mercy TAPE device (2D and 3D models) is intended to estimate the body weight of pediatric patients between the ages of 2 months and 16 years, using linear measurements from specific anatomical landmarks made with the Mercy TAPE device for humeral length (HL, for the 2D model) or half-humeral length (HHL, for the 3D model) and the mid-upper arm circumference (MUAC).

The Mercy TAPE device may be less reliable for use in children with known or apparent limb deformities, or abnormal body proportions caused by conditions such as edema or severe malnutrition.

The Mercy TAPE Device (2D and 3D Models) consists of semi-durable or disposable flexible strips of coated paper, fabric or plastic tape printed with numbered bins proportional to fractional body weight of pediatric patients. The markings correspond to the validated Mercy Method (calculation algorithm) for determining pediatric body weight using humeral length and mid-upper arm circumference.

The Mercy TAPE Device 2D Model consists of a single strip of tape that is used in two (2) stages to measure humeral length and mid-upper arm circumference. For the Mercy TAPE Device 3D Model, two (2) perpendicular strips of tape are designed to be joined into a sliding "T" shape so that humeral length and mid-upper arm circumference can be measured.

The provided text describes the Mercy TAPE device, which estimates pediatric patient body weight using linear measurements. While the document mentions clinical studies and a human factors/usability study, it does not explicitly define acceptance criteria in a quantifiable manner (e.g., "The device must achieve an accuracy of X% within Y kg"). Instead, it broadly states that "the device shows acceptably small variability from true weight with minimal bias" and that "the estimated weights generated by the Mercy TAPE Device (2D and 3D Models) are more accurate than the weights returned with existing weight estimation strategies."

It also states that the device was "validated against a mechanical scale to demonstrate equivalent performance," but the specific metrics and thresholds for this equivalence are not provided.

Therefore, I will extrapolate the "acceptance criteria" based on the general statements of acceptable performance and the study's conclusions, and then provide the reported performance based on the descriptions of the clinical studies.

Here's the information structured as requested, with details extracted from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note: As explicit quantitative acceptance criteria were not stated, these are inferred from the study's conclusions regarding acceptable performance and equivalence.

2. Sample Size Used for the Test Set and Data Provenance

The document describes several clinical studies. It seems the "clinical studies" mentioned in Section H encompass both the algorithm development/validation and a separate human factors study.

• Algorithm Validation (Test Set):

  • Sample size: 1,938 datasets
  • Data Provenance: Not explicitly stated for the validation set, but the underlying algorithm was developed using data from the National Health and Nutrition Examination Survey (NHANES) database. NHANES data is collected in the United States, so the provenance is likely United States.
  • Retrospective/Prospective: The use of "datasets" from NHANES suggests a retrospective analysis of existing data for algorithm development and validation.

• Human Factors/Usability Study (Test Set):

  • Sample size: 1,412 assessments (performed by healthcare providers). This implies that a number of pediatric patients were assessed multiple times. The exact number of unique "patients" in this study is not specified, but the number of "assessments" is 1,412.
  • Data Provenance: Not specified, but given the context of Children's Mercy Hospital in Kansas City, MO, it is likely United States.
  • Retrospective/Prospective: These were active "assessments" comparing the device to other strategies, so this was likely a prospective study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

• The document does not specify the number or qualifications of experts used to establish ground truth for either the algorithm validation or the human factors study.
• The ground truth for weight was established using "scales that use mechanical strain or balance methods" for comparison, which implies a direct measurement, not an expert consensus for the "true weight."

4. Adjudication Method for the Test Set

• The document does not describe any adjudication method for the test set. The ground truth appears to be based on objective measurements (mechanical scales), removing the need for expert adjudication.

5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study

• Yes, a MRMC-like study was done in the context of the human factors/usability study.
• The human factors study evaluated "front-line" healthcare providers (ED nurses and first responders) comparing the Mercy TAPE device against five other weight estimation strategies. This involves multiple "readers" (healthcare providers) evaluating cases (presumably pediatric patients).
• Effect size of how much human readers improve with AI vs without AI assistance: The document states that the Mercy TAPE device yielded "more accurate" estimated weights than existing strategies, even when factoring in errors and close-calls. However, it does not provide a specific quantitative effect size (e.g., percentage improvement in accuracy, reduction in error margin) for this improvement.

6. Standalone (Algorithm Only) Performance

• Yes, a standalone performance evaluation was done. The "clinical studies" section states: "Clinical studies were conducted to evaluate the predictive performance of the Mercy TAPE Device (2D and 3D Models) and their equivalence to the underlying Mercy Tape method algorithm." This primarily refers to the algorithm's performance in estimating weight.
• This performance was described as showing "acceptably small variability from true weight with minimal bias."

7. Type of Ground Truth Used

• The ground truth used for weight estimation was direct measurement from mechanical scales (e.g., "scales that use mechanical strain or balance methods"). This is an objective measurement, not expert consensus, pathology, or outcomes data.

8. Sample Size for the Training Set

• The Mercy Tape method algorithm was developed using "demographic and anthropometric data on 17,328 individual children." This represents the training/development set.

9. How the Ground Truth for the Training Set Was Established

• The ground truth for the training set (17,328 children) was established using data from the National Health and Nutrition Examination Survey (NHANES) database. NHANES collects comprehensive health and nutrition data, which includes anthropometric measurements and likely objective weight measurements, establishing the ground truth for algorithm development.

Ask a specific question about this device